Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Timothy Bastian Sianturi
Fakultas Ilmu Komputer, Universitas Brawijaya
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Penerapan Algoritma Long Short-Term Memory (LSTM) berbasis Multi Fungsi Aktivasi Terbobot dalam Prediksi Harga Ethereum Timothy Bastian Sianturi; Imam Cholissodin; Novanto Yudistira
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 7 No 3 (2023): Maret 2023
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

One form of innovation of technological development is cryptocurrencies that have been widely recognized as an alternative to currency exchange. One of the cryptocurrencies that is quite popular today is Ethereum which started trading for the first time on August 7, 2015 at a price of US$2.83 and reached its highest price on November 8, 2021 at a price of US$4822.97. Ethereum has high price fluctuations and has many factors that affect the price of ethereum such as political or economic problems at the global level so as to cause sufficient investment risk This research performs several stages in predicting ethereum price movements, namely pre-processing, data normalization, training Long Short-Term Memory (LSTM) algorithms, and evaluating with Mean Square Error (MSE). Based on the results of this study, researchers succeeded in predicting the price of Ethereum using the multi-function activation based LSTM algorithm with testing parameters for the proportion of training data and testing data of 70%:30%, the number of sequences of 14 which describes data for 14 days, the hidden unit value of 64, the number of epochs of 150, and sigmoid as an activation function as evidenced by the MSE value of 0.0121..
Co-Authors Imam Cholissodin Novanto Yudistira